From 5a08cb79bdc9cab781b80bf804c51dc444fbf70c Mon Sep 17 00:00:00 2001
From: "Fred N. Garvin" <184324400+FNGarvin@users.noreply.github.com>
Date: Thu, 21 Nov 2024 18:13:17 -0600
Subject: [PATCH 1/2] Update model.py to enable CUDA when available

Shell out to nvidia-smi for NVidia detection, add device or gpu args to conman as appropriate for docker vs podman

Signed-off-by: Fred N. Garvin, Esq. <184324400+FNGarvin@users.noreply.github.com>
---
 ramalama/model.py | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/ramalama/model.py b/ramalama/model.py
index 5ee217bc..54ac693c 100644
--- a/ramalama/model.py
+++ b/ramalama/model.py
@@ -152,6 +152,16 @@ def setup_container(self, args):
         gpu_type, gpu_num = get_gpu()
         if gpu_type == "HIP_VISIBLE_DEVICES" or gpu_type == "ASAHI_VISIBLE_DEVICES":
             conman_args += ["-e", f"{gpu_type}={gpu_num}"]
+
+        #podman is not a drop-in replacement for docker... need to "see" which we're in here, ala common.py->available logic
+        #risk of duplicating code here, maint problem
+        if gpu_type == "CUDA_VISIBLE_DEVICES":
+            if shutil.which("podman"):
+                #todo is /all/ appropriate?
+                conman_args += ["--device", "nvidia.com/gpu=all"] #AFAIK, cuda requires this for podman
+            else:
+                conman_args += ["--gpus", "all"] #and this for Docker
+        
         return conman_args
 
     def run_container(self, args, shortnames):
@@ -389,7 +399,15 @@ def get_gpu():
             content = file.read()
             if "asahi" in content.lower():
                 return "ASAHI_VISIBLE_DEVICES", 1
-
+                
+    try:
+        #TODO I don't currently have access to a PC w/ multiple NVidia GPUs nor an NVidia Mac...  but I *think* that
+        #every Linux and Windows machine having modern NVidia will have nvidia-smi and that the number of lines corresponds to the number of zero-indexed gpus
+        check_output = subprocess.run(['nvidia-smi', '-L'], check=True, capture_output=True) #shell to nvidia-smi
+        if not check_output.returncode: #if command EXIT_SUCCESS
+            return "CUDA_VISIBLE_DEVICES", len(check_output.stdout.splitlines()) # ret cuda, #gpus?
+    except Exception: {} #fall through
+    
     return None, None
 
 

From c638d979a69a20d3c2fe6feb93843828ed979159 Mon Sep 17 00:00:00 2001
From: "Fred N. Garvin" <184324400+FNGarvin@users.noreply.github.com>
Date: Thu, 21 Nov 2024 18:36:52 -0600
Subject: [PATCH 2/2] Update model.py

import subprocess (to shell out for nvidia-smi) and shutil (to duplicate available() functionality and test whether we're in podman or docker

Signed-off-by: Fred N. Garvin, Esq. <184324400+FNGarvin@users.noreply.github.com>
---
 ramalama/model.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ramalama/model.py b/ramalama/model.py
index 54ac693c..2514fed4 100644
--- a/ramalama/model.py
+++ b/ramalama/model.py
@@ -3,6 +3,8 @@
 import glob
 import atexit
 import shlex
+import subprocess
+import shutil
 
 from ramalama.common import (
     default_image,